From 32ebe6e81231a7f2a2fd14c27b40e6f7b4abe02d Mon Sep 17 00:00:00 2001 From: Peter Jun Park Date: Mon, 17 Jun 2024 01:37:09 -0400 Subject: [PATCH] clean up index Signed-off-by: Peter Jun Park --- docs/index.rst | 62 +++++++++++++++--------- docs/what-is-omniperf.rst | 99 +++++++++++++++++---------------------- 2 files changed, 81 insertions(+), 80 deletions(-) diff --git a/docs/index.rst b/docs/index.rst index 2cffbed52..e5298122c 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -2,48 +2,64 @@ :description: Omniperf documentation and reference :keywords: Omniperf, ROCm, profiler, tool, Instinct, accelerator, AMD -********************** -Omniperf documentation -********************** +******** +Omniperf +******** Omniperf documentation provides a detailed breakdown of all facets of Omniperf. -In addition to a full deployment guide with installation instructions, we also -explain the design of the tool and each of its components. +In addition to a full deployment guide with installation instructions, this +documentation also explains the ideas motivating the design behind the tool and +its components. -If you're new to Omniperf, gradually acquaint yourself with the tool by -following the chapters that following and progressively learn its more advanced -features. To get started, see :doc:`What is Omniperf? `. +If you're new to Omniperf, acquaint yourself with the tool by reviewing the +chapters that follow and gradually learn its more advanced features. To get +started, see :doc:`What is Omniperf? `. See Omniperf source code at ``__. .. grid:: 2 - :gutter: 3 + :gutter: 3 - .. grid-item-card:: Install + .. grid-item-card:: Install - * :doc:`Quick start ` - * :doc:`Install Omniperf ` + * :doc:`install/quick-start` + * :doc:`install/omniperf` - .. grid-item-card:: Conceptual + .. grid-item:: - * :doc:`High-level design of Omniperf ` - * :doc:`Performance model ` +Use the following topics to learn more about the advantages of Omniperf in your +development toolkit, how it aims to model performance, and how to use Omniperf +in practice. - .. grid-item-card:: How to +.. grid:: 2 + :gutter: 3 + + .. grid-item-card:: Conceptual + + * :doc:`conceptual/overview` + * :doc:`conceptual/performance-model` + + .. grid-item-card:: How to - * :doc:`Profiling ` - * :doc:`Analysis ` + * :doc:`how-to/profiling` + * :doc:`how-to/analysis` - .. grid-item-card:: Reference + .. grid-item-card:: Tutorials - * :doc:`FAQ ` - * :doc:`Glossary ` + * `Omniperf example exercises `_ -This project is proudly open source and we welcome all feedback! For more + .. grid-item-card:: Reference + + * :doc:`reference/compatible-accelerators` + * :doc:`reference/faq` + * :doc:`reference/glossary` + * :doc:`license` + + +This project is proudly open source and we welcome all feedback. For more details on how to contribute, refer to `Contributing to ROCm `_. Find licensing information on the `Licensing `_ page. - diff --git a/docs/what-is-omniperf.rst b/docs/what-is-omniperf.rst index 076cf1f76..90e3a000f 100644 --- a/docs/what-is-omniperf.rst +++ b/docs/what-is-omniperf.rst @@ -1,3 +1,7 @@ +.. meta:: + :description: What is Omniperf? + :keywords: Omniperf, ROCm, profiler, tool, Instinct, accelerator, AMD + ***************** What is Omniperf? ***************** @@ -8,70 +12,51 @@ running on AMD Instinct™ accelerators. AMD Instinct MI-series accelerators are data center-class GPUs designed for compute and have some graphics capabilities disabled or removed. Omniperf primarily targets use with -:doc:`accelerators in the MI100, MI200, and MI300 families `. +:doc:`accelerators in the MI300, MI200, and MI100 families `. Development is in progress to support Radeon™ (RDNA) GPUs. Omniperf is built on top of :doc:`ROCProfiler ` to monitor hardware performance counters. -Features -======== +Omniperf features +================= -Omniperf performs profiling based on all available hardware counters for the -target accelerator. It provides high-level performance analysis features -including System Speed of Light (SOL), Hardware block-level SOL, Memory Chart -Analysis, Roofline Analysis, Baseline Comparisons, and more. +Omniperf offers comprehensive profiling based on all available hardware counters +for the target accelerator. It delivers advanced performance analysis features, +such as system speed-of-light (SOL) and hardware block-level SOL evaluations. +Additionally, Omniperf provides in-depth memory chart analysis, roofline +analysis, baseline comparisons, and more, ensuring a thorough understanding of +system performance. Omniperf supports both command line analysis and GUI analysis. -Detailed feature list: - -- MI100 support -- MI200 support -- MI300 support -- Standalone GUI Analyzer -- Grafana/MongoDB GUI Analyzer -- Dispatch Filtering -- Kernel Filtering -- GPU ID Filtering -- Baseline Comparison -- Multi-Normalizations -- System Info Panel -- System Speed-of-Light Panel -- Kernel Statistic Panel -- Memory Chart Analysis Panel -- Roofline Analysis Panel (*Supported on MI200 only, Ubuntu 20.04, SLES 15 SP3 or RHEL8*) -- Command Processor (CP) Panel -- Workgroup Manager (SPI) Panel -- Wavefront Launch Panel -- Compute Unit - Instruction Mix Panel -- Compute Unit - Pipeline Panel -- Local Data Share (LDS) Panel -- Instruction Cache Panel -- Scalar L1D Cache Panel -- L1 Address Processing Unit, a.k.a. Texture Addresser (TA) / L1 Backend Data Processing Unit, a.k.a. Texture Data (TD) - panel(s) -- Vector L1D Cache Panel -- L2 Cache Panel -- L2 Cache (per-Channel) Panel - -Compatible SoCs -=============== - -.. list-table:: - :header-rows: 1 - - * - Platform - - Status - - * - Vega 20 (MI50/60) - - No support - - * - MI100 - - Supported - - * - MI200 - - Supported +Detailed feature list +--------------------- + +* :doc:`Support for MI300, MI200, and MI100 ` +* Standalone GUI analyzer +* GUI analyzer via Grafana and MongoDB +* Dispatch filtering +* Kernel filtering +* GPU ID filtering +* Baseline comparison +* Multiple normalizations +* *System info* panel +* *System Speed-of-Light* panel +* *Kernel Statistic* panel +* *Memory Chart Analysis* panel +* *Roofline Analysis* panel (*Supported on MI200 only, Ubuntu 20.04, SLES 15 SP3 or RHEL8*) +* *Command Processor (CP)* panel +* *Workgroup Manager (SPI)* panel +* *Wavefront Launch* Panel +* *Compute Unit - Instruction Mix* panel +* *Compute Unit - Pipeline* panel +* *Local Data Share (LDS)* panel +* *Instruction Cache* panel +* *Scalar L1D Cache* panel +* *L1 Address Processing Unit*, or, *Texture Addresser (TA)* and + *L1 Backend Data Processing Unit*, or, *Texture Data (TD)* panels +* *Vector L1D Cache* panel +* *L2 Cache* panel +* *L2 Cache (per-channel)* panel - * - MI300 - - Supported